Crossmodal Matching of Speakers Using Lip and Voice Features in Temporally Non-overlapping Audio and Video Streams.
Anindya RoySébastien MarcelPublished in: ICPR (2010)
Keyphrases
- video streams
- video data
- video clips
- audio stream
- feature matching
- multimedia
- keypoints
- feature vectors
- low level
- video segments
- feature extraction
- matching process
- feature space
- video content
- temporal information
- spatio temporal
- feature set
- visual information
- image matching
- feature descriptors
- object tracking
- matching algorithm
- digital video
- soccer video
- video representation
- e learning